Matthew E. Taylor
YOU?
Author Swipe
View article: Pilot Trainees Benefit from Modelling and Adaptive Feedback
Pilot Trainees Benefit from Modelling and Adaptive Feedback Open
View article: A Call to Arms: Automated Methods for Identifying Weapons in Social Media Analysis of Conflict Zones
A Call to Arms: Automated Methods for Identifying Weapons in Social Media Analysis of Conflict Zones Open
View article: A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs
A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs Open
With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In…
View article: An LLM-Guided Tutoring System for Social Skills Training
An LLM-Guided Tutoring System for Social Skills Training Open
Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication — one-to-one interaction in real-world sc…
View article: Model-Based Exploration in Monitored Markov Decision Processes
Model-Based Exploration in Monitored Markov Decision Processes Open
A tenet of reinforcement learning is that the agent always observes rewards. However, this is not true in many realistic settings, e.g., a human observer may not always be available to provide rewards, sensors may be limited or malfunction…
View article: An LLM-Guided Tutoring System for Social Skills Training
An LLM-Guided Tutoring System for Social Skills Training Open
Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication -- one-to-one interaction in real-world s…
View article: Decentralized coordination of distributed energy resources through local energy markets and deep reinforcement learning
Decentralized coordination of distributed energy resources through local energy markets and deep reinforcement learning Open
As the energy landscape evolves towards sustainability, the accelerating integration of distributed energy resources poses challenges to the operability and reliability of the electricity grid. One significant aspect of this issue is the n…
View article: Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation
Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation Open
As robots become more common for both able-bodied individuals and those living with a disability, it is increasingly important that lay people be able to drive multi-degree-of-freedom platforms with low-dimensional controllers. One approac…
View article: A novel framework for automated warehouse layout generation
A novel framework for automated warehouse layout generation Open
Optimizing warehouse layouts is crucial due to its significant impact on efficiency and productivity. We present an AI-driven framework for automated warehouse layout generation. This framework employs constrained beam search to derive opt…
View article: CANDERE-COACH: Reinforcement Learning from Noisy Feedback
CANDERE-COACH: Reinforcement Learning from Noisy Feedback Open
In recent times, Reinforcement learning (RL) has been widely applied to many challenging tasks. However, in order to perform well, it requires access to a good reward function which is often sparse or manually engineered with scope for err…
View article: A Novel Framework for Automated Warehouse Layout Generation
A Novel Framework for Automated Warehouse Layout Generation Open
Optimizing warehouse layouts is crucial due to its significant impact on efficiency and productivity. We present an AI-driven framework for automated warehouse layout generation. This framework employs constrained beam search to derive opt…
View article: Video Occupancy Models
Video Occupancy Models Open
We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about…
View article: Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity Open
To integrate into human-centered environments, autonomous agents must learn from and adapt to humans in their native settings. Preference-based reinforcement learning (PbRL) can enable this by learning reward functions from human preferenc…
View article: Applying reinforcement learning to learn best net to rip and re-route in global routing
Applying reinforcement learning to learn best net to rip and re-route in global routing Open
Physical designers typically employ heuristics to solve challenging problems in global routing. However, these heuristic solutions are not adaptable to the ever-changing fabrication demands, and the experience and creativity of designers c…
View article: Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning
Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning Open
To create useful reinforcement learning (RL) agents, step zero is to design a suitable reward function that captures the nuances of the task. However, reward engineering can be a difficult and time-consuming process. Instead, human-in-the-…
View article: Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning
Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning Open
As distributed energy resources (DERs) grow, the electricity grid faces increased net load variability at the grid edge, impacting operability and reliability. Transactive energy, facilitated through local energy markets, offers a decentra…
View article: FPGA Divide-and-Conquer Placement using Deep Reinforcement Learning
FPGA Divide-and-Conquer Placement using Deep Reinforcement Learning Open
This paper introduces the problem of learning to place logic blocks in Field-Programmable Gate Arrays (FPGAs) and a learning-based method. In contrast to previous search-based placement algorithms, we instead employ Reinforcement Learning …
View article: A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning
A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning Open
Transfer learning (TL) has shown great potential to improve Reinforcement Learning (RL) efficiency by leveraging prior knowledge in new tasks. However, much of the existing TL research focuses on transferring knowledge between tasks that s…
View article: PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning
PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning Open
Despite many breakthroughs in recent years, it is still hard for MultiAgent Reinforcement Learning (MARL) algorithms to directly solve complex tasks in MultiAgent Systems (MASs) from scratch. In this work, we study how to use Automatic Cur…
View article: Monitored Markov Decision Processes
Monitored Markov Decision Processes Open
In reinforcement learning (RL), an agent learns to perform a task by interacting with an environment and receiving feedback (a numerical reward) for its actions. However, the assumption that rewards are always observable is often not appli…
View article: Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities
Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities Open
Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (…
View article: GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
GLIDE-RL: Grounded Language Instruction through DEmonstration in RL Open
One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL)…
View article: LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models
LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models Open
Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired …
View article: MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning Open
The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabl…
View article: Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning
Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning Open
While there has been significant progress in curriculum learning and continuous learning for training agents to generalize across a wide variety of environments in the context of single-agent reinforcement learning, it is unclear if these …
View article: Human-Machine Teaming for UAVs: An Experimentation Platform
Human-Machine Teaming for UAVs: An Experimentation Platform Open
Full automation is often not achievable or desirable in critical systems with high-stakes decisions. Instead, human-AI teams can achieve better results. To research, develop, evaluate, and validate algorithms suited for such teaming, light…
View article: A Call to Arms: AI Should be Critical for Social Media Analysis of Conflict Zones
A Call to Arms: AI Should be Critical for Social Media Analysis of Conflict Zones Open
The massive proliferation of social media data represents a transformative opportunity for conflict studies and for tracking the proliferation and use of weaponry, as conflicts are increasingly documented in these online spaces. At the sam…
View article: Can You Improve My Code? Optimizing Programs with Local Search
Can You Improve My Code? Optimizing Programs with Local Search Open
This paper introduces a local search method for improving an existing program with respect to a measurable objective. Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines. POL…
View article: Multi-Agent Advisor Q-Learning (Extended Abstract)
Multi-Agent Advisor Q-Learning (Extended Abstract) Open
In the last decade, there have been significant advances in multi-agent reinforcement learning (MARL) but there are still numerous challenges, such as high sample complexity and slow convergence to stable policies, that need to be overcome…
View article: Can You Improve My Code? Optimizing Programs with Local Search
Can You Improve My Code? Optimizing Programs with Local Search Open
This paper introduces a local search method for improving an existing program with respect to a measurable objective. Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines. POL…